Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 718 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6927. Min Range: -8.6927
Max Act: 8.6927. Min Act: -0.1700
Data Index: 1643762 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6927. Min Range: -8.6927
Max Act: 8.6302. Min Act: -0.1700
Data Index: 2763793 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.8177. Min Act: -0.1700
Data Index: 2445936 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.7552. Min Act: -0.1700
Data Index: 8436908 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.7552. Min Act: -0.1700
Data Index: 7932045 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.6927. Min Act: -0.1700
Data Index: 4103396 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.6302. Min Act: -0.1700
Data Index: 5026322 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.6302. Min Act: -0.1700
Data Index: 469714 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.5677. Min Act: -0.1700
Data Index: 5813305 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.6302. Min Act: -0.1700
Data Index: 2767504 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.5364. Min Act: -0.1700
Data Index: 2179139 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.5677. Min Act: -0.1700
Data Index: 2800328 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.5677. Min Act: -0.1700
Data Index: 2549395 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.5677. Min Act: -0.1700
Data Index: 7258674 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.5677. Min Act: -0.1700
Data Index: 2680170 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.5364. Min Act: -0.1700
Data Index: 7278163 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.5052. Min Act: -0.1700
Data Index: 4204563 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.4739. Min Act: -0.1700
Data Index: 7900151 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.5052. Min Act: -0.1700
Data Index: 1014832 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6927. Min Range: -8.6927
Max Act: 7.4739. Min Act: -0.1700
Data Index: 5644086 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19